DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Four levers that cut an LLM API bill by ~87%, with the math

Four levers that cut an LLM API bill by ~87%, with the math

Comments
3 min read
OpenAI's Own AI Broke Out of Its Sandbox and Hacked Another Company — To Cheat on a Test

OpenAI's Own AI Broke Out of Its Sandbox and Hacked Another Company — To Cheat on a Test

Comments 1
7 min read
Medir si un LLM nombra a tu empresa: por qué una captura no sirve como métrica

Medir si un LLM nombra a tu empresa: por qué una captura no sirve como métrica

1
Comments
4 min read
멀티 에이전트 동시성 예외를 디버깅하고 동기화하는 구조 설계

멀티 에이전트 동시성 예외를 디버깅하고 동기화하는 구조 설계

Comments
2 min read
What does your AI assistant remember from yesterday?

What does your AI assistant remember from yesterday?

6
Comments 4
4 min read
Don't Ask What Do You Like. Ask Where Would You Find It.

Don't Ask What Do You Like. Ask Where Would You Find It.

Comments
3 min read
DeepSeek API in TypeScript: secure integration and honest model evaluation for code

DeepSeek API in TypeScript: secure integration and honest model evaluation for code

2
Comments
7 min read
Passing Once Isn't Reliable — This Week's Agent Engineering Puts the Harness Before the Model

Passing Once Isn't Reliable — This Week's Agent Engineering Puts the Harness Before the Model

Comments
6 min read
Soft Alerts Don’t Stop Agent Spend. Hard Budgets Do.

Soft Alerts Don’t Stop Agent Spend. Hard Budgets Do.

1
Comments
2 min read
Your AI Gateway Needs a Conversion Graph, Not a Pile of If Statements

Your AI Gateway Needs a Conversion Graph, Not a Pile of If Statements

Comments
8 min read
Qwen3.8-Max-Preview and Kimi’s Subscription Freeze Reveal the Real AI Competition

Qwen3.8-Max-Preview and Kimi’s Subscription Freeze Reveal the Real AI Competition

Comments
6 min read
My Local LLM Was Running at 1.6% of Its Context. Here's the Setting That Fixed It

My Local LLM Was Running at 1.6% of Its Context. Here's the Setting That Fixed It

Comments
3 min read
A small model on a 6GB laptop beat Claude Opus on one 440K-token question. The fix was giving the model less to do.

A small model on a 6GB laptop beat Claude Opus on one 440K-token question. The fix was giving the model less to do.

1
Comments 1
5 min read
Small Model SWE‑bench: What Happens When You Push Tiny Models Into Full Task Pipelines

Small Model SWE‑bench: What Happens When You Push Tiny Models Into Full Task Pipelines

Comments
2 min read
LLM Finetunings, how and why

LLM Finetunings, how and why

Comments 1
9 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.